Artificial Intelligence, IASLC Grading System, Lung Adenocarcinoma, Whole Slide Image
Conditions
Brief summary
The purpose of this study is to evaluate the performance of a whole slide image based deep learning model for diagnosing the IASLC grading system in resected lung adenocarcinoma based on a multicenter prospective cohort.
Interventions
DIAGNOSTIC_TESTWhole Slide Image based Deep Learning
Whole Slide Image Based Deep Learning for Diagnosing the IASLC Grading System of Lung Adenocarcinoma
Sponsors
Shanghai Pulmonary Hospital, Shanghai, China
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 85 Years
Inclusion criteria
1. Age ranging from 18-85 years old; 2. Pathological confirmation of primary lung adenocarcinoma after surgery; 3. Obtained written informed consent.
Exclusion criteria
1. Multiple lung lesions; 2. Poor quality of whole slide images; 3. Mucinous adenocarcinomas and variants; 4. Participants who have received neoadjuvant therapy.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Agreement rate of the IASLC grading system | 2024.11.01-2024.12.31 | Agreement rate between the deep learning model and pathologists in diagnosing the IASLC grade of lung adenocarcinoma. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Agreement rate of the predominant subtypes | 2024.11.01-2024.12.31 | Agreement rate between the deep learning model and pathologists in diagnosing the predominant growth patterns of lung adenocarcinoma. |
Countries
China
Outcome results
None listed